Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Facial Feedback Hypothesis01:24

Facial Feedback Hypothesis

139
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
139

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Adaptive Gating and Focal Debiasing for robust few-shot retinal disease classification.

Frontiers in artificial intelligence·2026
Same author

A systematic review investigating emerging trends between Extreme Weather Events (EWEs) and infectious disease outbreaks in South Africa.

Frontiers in public health·2026
Same author

Editorial: Soft computing and machine learning applications for healthcare systems.

Frontiers in artificial intelligence·2026
Same author

Correction: Zeng et al. High-Performance Silicon Nanowire Array Biosensor for Combined Detection of Colorectal Cancer Biomarkers. <i>Micromachines</i> 2025, <i>16</i>, 1089.

Micromachines·2025
Same author

High-Performance Silicon Nanowire Array Biosensor for Combined Detection of Colorectal Cancer Biomarkers.

Micromachines·2025
Same author

Deep Learning Techniques for Prostate Cancer Analysis and Detection: Survey of the State of the Art.

Journal of imaging·2025

相关实验视频

Updated: Jun 24, 2025

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

使用视觉转换器增强语音情感识别.

Samson Akinpelu1, Serestina Viriri2, Adekanmi Adegun1

  • 1School of Mathematics, Statistics and Computer Science, University of KwaZulu-Natal, Durban, 4001, South Africa.

Scientific reports
|June 7, 2024
PubMed
概括

这项研究引入了一种使用视觉转换器 (ViT) 进行语音情感识别 (SER) 的新方法,实现了高精度. 这种方法有效地捕捉了来自Mel光谱的情感线索,增强了人机交互系统.

关键词:
在美国,CNN是CNN.深度学习是一种深度学习.人与计算机的互动.梅尔的光谱图 (Mel spectrogram) 是一个光谱图.语音 情感识别 语音 情感识别视觉变压器 视觉变压器

更多相关视频

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

相关实验视频

Last Updated: Jun 24, 2025

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 人与计算机的交互

背景情况:

  • 传统上,语音情感识别 (SER) 依赖于声学特征.
  • 深度学习和计算机视觉的进步使多模式SER成为可能.
  • 整合视觉特征可以显著提高SER性能.

研究的目的:

  • 提出一种用于增强语音情感识别 (SER) 的新方法,使用轻量级视觉变压器 (ViT).
  • 为了利用ViT在捕捉情绪检测的空间和高层特征从Mel光谱图的能力.
  • 在基准数据集上评估拟议方法的有效性.

主要方法:

  • 使用了一种轻量级的视觉变压器 (ViT) 模型.
  • 处理的Mel光谱图作为ViT模型的输入.
  • 采用非重叠的基于补丁的特征提取方法.

主要成果:

  • 实现了高准确率:TESS上的98%,EMODB上的91%,TESS-EMODB上的93%.
  • 在SER准确性和通用性方面表现出显著的改进.
  • 不重叠的基于补丁的特征提取方法显著提高了SER.

结论:

  • 拟议的基于ViT的方法在语音情感识别方面取得了重大进展.
  • 视觉变压器模型显示了集成到SER系统的巨大潜力.
  • 这项研究为现实世界的应用开辟了新的途径,这些应用需要从语音中准确识别情绪.